From cde9070d9970eef1f7ec2360586c802a16230ad8 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Fri, 10 May 2024 07:43:50 +0000
Subject: [PATCH] rtl88x2CE_WiFi_linux driver
---
kernel/kernel/irq/affinity.c | 426 ++++++++++++++++++++++++++++++++++++++++++-----------
1 files changed, 336 insertions(+), 90 deletions(-)
diff --git a/kernel/kernel/irq/affinity.c b/kernel/kernel/irq/affinity.c
index e12cdf6..5fb78ad 100644
--- a/kernel/kernel/irq/affinity.c
+++ b/kernel/kernel/irq/affinity.c
@@ -7,9 +7,10 @@
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/cpu.h>
+#include <linux/sort.h>
static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
- int cpus_per_vec)
+ unsigned int cpus_per_vec)
{
const struct cpumask *siblmsk;
int cpu, sibl;
@@ -94,17 +95,168 @@
return nodes;
}
-static int irq_build_affinity_masks(const struct irq_affinity *affd,
- int startvec, int numvecs,
- cpumask_var_t *node_to_cpumask,
- const struct cpumask *cpu_mask,
- struct cpumask *nmsk,
- struct cpumask *masks)
+struct node_vectors {
+ unsigned id;
+
+ union {
+ unsigned nvectors;
+ unsigned ncpus;
+ };
+};
+
+static int ncpus_cmp_func(const void *l, const void *r)
{
- int n, nodes, cpus_per_vec, extra_vecs, done = 0;
- int last_affv = affd->pre_vectors + numvecs;
- int curvec = startvec;
+ const struct node_vectors *ln = l;
+ const struct node_vectors *rn = r;
+
+ return ln->ncpus - rn->ncpus;
+}
+
+/*
+ * Allocate vector number for each node, so that for each node:
+ *
+ * 1) the allocated number is >= 1
+ *
+ * 2) the allocated numbver is <= active CPU number of this node
+ *
+ * The actual allocated total vectors may be less than @numvecs when
+ * active total CPU number is less than @numvecs.
+ *
+ * Active CPUs means the CPUs in '@cpu_mask AND @node_to_cpumask[]'
+ * for each node.
+ */
+static void alloc_nodes_vectors(unsigned int numvecs,
+ cpumask_var_t *node_to_cpumask,
+ const struct cpumask *cpu_mask,
+ const nodemask_t nodemsk,
+ struct cpumask *nmsk,
+ struct node_vectors *node_vectors)
+{
+ unsigned n, remaining_ncpus = 0;
+
+ for (n = 0; n < nr_node_ids; n++) {
+ node_vectors[n].id = n;
+ node_vectors[n].ncpus = UINT_MAX;
+ }
+
+ for_each_node_mask(n, nodemsk) {
+ unsigned ncpus;
+
+ cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]);
+ ncpus = cpumask_weight(nmsk);
+
+ if (!ncpus)
+ continue;
+ remaining_ncpus += ncpus;
+ node_vectors[n].ncpus = ncpus;
+ }
+
+ numvecs = min_t(unsigned, remaining_ncpus, numvecs);
+
+ sort(node_vectors, nr_node_ids, sizeof(node_vectors[0]),
+ ncpus_cmp_func, NULL);
+
+ /*
+ * Allocate vectors for each node according to the ratio of this
+ * node's nr_cpus to remaining un-assigned ncpus. 'numvecs' is
+ * bigger than number of active numa nodes. Always start the
+ * allocation from the node with minimized nr_cpus.
+ *
+ * This way guarantees that each active node gets allocated at
+ * least one vector, and the theory is simple: over-allocation
+ * is only done when this node is assigned by one vector, so
+ * other nodes will be allocated >= 1 vector, since 'numvecs' is
+ * bigger than number of numa nodes.
+ *
+ * One perfect invariant is that number of allocated vectors for
+ * each node is <= CPU count of this node:
+ *
+ * 1) suppose there are two nodes: A and B
+ * ncpu(X) is CPU count of node X
+ * vecs(X) is the vector count allocated to node X via this
+ * algorithm
+ *
+ * ncpu(A) <= ncpu(B)
+ * ncpu(A) + ncpu(B) = N
+ * vecs(A) + vecs(B) = V
+ *
+ * vecs(A) = max(1, round_down(V * ncpu(A) / N))
+ * vecs(B) = V - vecs(A)
+ *
+ * both N and V are integer, and 2 <= V <= N, suppose
+ * V = N - delta, and 0 <= delta <= N - 2
+ *
+ * 2) obviously vecs(A) <= ncpu(A) because:
+ *
+ * if vecs(A) is 1, then vecs(A) <= ncpu(A) given
+ * ncpu(A) >= 1
+ *
+ * otherwise,
+ * vecs(A) <= V * ncpu(A) / N <= ncpu(A), given V <= N
+ *
+ * 3) prove how vecs(B) <= ncpu(B):
+ *
+ * if round_down(V * ncpu(A) / N) == 0, vecs(B) won't be
+ * over-allocated, so vecs(B) <= ncpu(B),
+ *
+ * otherwise:
+ *
+ * vecs(A) =
+ * round_down(V * ncpu(A) / N) =
+ * round_down((N - delta) * ncpu(A) / N) =
+ * round_down((N * ncpu(A) - delta * ncpu(A)) / N) >=
+ * round_down((N * ncpu(A) - delta * N) / N) =
+ * cpu(A) - delta
+ *
+ * then:
+ *
+ * vecs(A) - V >= ncpu(A) - delta - V
+ * =>
+ * V - vecs(A) <= V + delta - ncpu(A)
+ * =>
+ * vecs(B) <= N - ncpu(A)
+ * =>
+ * vecs(B) <= cpu(B)
+ *
+ * For nodes >= 3, it can be thought as one node and another big
+ * node given that is exactly what this algorithm is implemented,
+ * and we always re-calculate 'remaining_ncpus' & 'numvecs', and
+ * finally for each node X: vecs(X) <= ncpu(X).
+ *
+ */
+ for (n = 0; n < nr_node_ids; n++) {
+ unsigned nvectors, ncpus;
+
+ if (node_vectors[n].ncpus == UINT_MAX)
+ continue;
+
+ WARN_ON_ONCE(numvecs == 0);
+
+ ncpus = node_vectors[n].ncpus;
+ nvectors = max_t(unsigned, 1,
+ numvecs * ncpus / remaining_ncpus);
+ WARN_ON_ONCE(nvectors > ncpus);
+
+ node_vectors[n].nvectors = nvectors;
+
+ remaining_ncpus -= ncpus;
+ numvecs -= nvectors;
+ }
+}
+
+static int __irq_build_affinity_masks(unsigned int startvec,
+ unsigned int numvecs,
+ unsigned int firstvec,
+ cpumask_var_t *node_to_cpumask,
+ const struct cpumask *cpu_mask,
+ struct cpumask *nmsk,
+ struct irq_affinity_desc *masks)
+{
+ unsigned int i, n, nodes, cpus_per_vec, extra_vecs, done = 0;
+ unsigned int last_affv = firstvec + numvecs;
+ unsigned int curvec = startvec;
nodemask_t nodemsk = NODE_MASK_NONE;
+ struct node_vectors *node_vectors;
if (!cpumask_weight(cpu_mask))
return 0;
@@ -117,102 +269,103 @@
*/
if (numvecs <= nodes) {
for_each_node_mask(n, nodemsk) {
- cpumask_or(masks + curvec, masks + curvec, node_to_cpumask[n]);
+ /* Ensure that only CPUs which are in both masks are set */
+ cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]);
+ cpumask_or(&masks[curvec].mask, &masks[curvec].mask, nmsk);
if (++curvec == last_affv)
- curvec = affd->pre_vectors;
+ curvec = firstvec;
}
- done = numvecs;
- goto out;
+ return numvecs;
}
- for_each_node_mask(n, nodemsk) {
- int ncpus, v, vecs_to_assign, vecs_per_node;
+ node_vectors = kcalloc(nr_node_ids,
+ sizeof(struct node_vectors),
+ GFP_KERNEL);
+ if (!node_vectors)
+ return -ENOMEM;
- /* Spread the vectors per node */
- vecs_per_node = (numvecs - (curvec - affd->pre_vectors)) / nodes;
+ /* allocate vector number for each node */
+ alloc_nodes_vectors(numvecs, node_to_cpumask, cpu_mask,
+ nodemsk, nmsk, node_vectors);
+
+ for (i = 0; i < nr_node_ids; i++) {
+ unsigned int ncpus, v;
+ struct node_vectors *nv = &node_vectors[i];
+
+ if (nv->nvectors == UINT_MAX)
+ continue;
/* Get the cpus on this node which are in the mask */
- cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]);
-
- /* Calculate the number of cpus per vector */
+ cpumask_and(nmsk, cpu_mask, node_to_cpumask[nv->id]);
ncpus = cpumask_weight(nmsk);
- vecs_to_assign = min(vecs_per_node, ncpus);
+ if (!ncpus)
+ continue;
+
+ WARN_ON_ONCE(nv->nvectors > ncpus);
/* Account for rounding errors */
- extra_vecs = ncpus - vecs_to_assign * (ncpus / vecs_to_assign);
+ extra_vecs = ncpus - nv->nvectors * (ncpus / nv->nvectors);
- for (v = 0; curvec < last_affv && v < vecs_to_assign;
- curvec++, v++) {
- cpus_per_vec = ncpus / vecs_to_assign;
+ /* Spread allocated vectors on CPUs of the current node */
+ for (v = 0; v < nv->nvectors; v++, curvec++) {
+ cpus_per_vec = ncpus / nv->nvectors;
/* Account for extra vectors to compensate rounding errors */
if (extra_vecs) {
cpus_per_vec++;
--extra_vecs;
}
- irq_spread_init_one(masks + curvec, nmsk, cpus_per_vec);
+
+ /*
+ * wrapping has to be considered given 'startvec'
+ * may start anywhere
+ */
+ if (curvec >= last_affv)
+ curvec = firstvec;
+ irq_spread_init_one(&masks[curvec].mask, nmsk,
+ cpus_per_vec);
}
-
- done += v;
- if (done >= numvecs)
- break;
- if (curvec >= last_affv)
- curvec = affd->pre_vectors;
- --nodes;
+ done += nv->nvectors;
}
-
-out:
+ kfree(node_vectors);
return done;
}
-/**
- * irq_create_affinity_masks - Create affinity masks for multiqueue spreading
- * @nvecs: The total number of vectors
- * @affd: Description of the affinity requirements
- *
- * Returns the masks pointer or NULL if allocation failed.
+/*
+ * build affinity in two stages:
+ * 1) spread present CPU on these vectors
+ * 2) spread other possible CPUs on these vectors
*/
-struct cpumask *
-irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
+static int irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs,
+ unsigned int firstvec,
+ struct irq_affinity_desc *masks)
{
- int affvecs = nvecs - affd->pre_vectors - affd->post_vectors;
- int curvec, usedvecs;
- cpumask_var_t nmsk, npresmsk, *node_to_cpumask;
- struct cpumask *masks = NULL;
-
- /*
- * If there aren't any vectors left after applying the pre/post
- * vectors don't bother with assigning affinity.
- */
- if (nvecs == affd->pre_vectors + affd->post_vectors)
- return NULL;
+ unsigned int curvec = startvec, nr_present = 0, nr_others = 0;
+ cpumask_var_t *node_to_cpumask;
+ cpumask_var_t nmsk, npresmsk;
+ int ret = -ENOMEM;
if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
- return NULL;
+ return ret;
if (!zalloc_cpumask_var(&npresmsk, GFP_KERNEL))
- goto outcpumsk;
+ goto fail_nmsk;
node_to_cpumask = alloc_node_to_cpumask();
if (!node_to_cpumask)
- goto outnpresmsk;
-
- masks = kcalloc(nvecs, sizeof(*masks), GFP_KERNEL);
- if (!masks)
- goto outnodemsk;
-
- /* Fill out vectors at the beginning that don't need affinity */
- for (curvec = 0; curvec < affd->pre_vectors; curvec++)
- cpumask_copy(masks + curvec, irq_default_affinity);
+ goto fail_npresmsk;
/* Stabilize the cpumasks */
get_online_cpus();
build_node_to_cpumask(node_to_cpumask);
/* Spread on present CPUs starting from affd->pre_vectors */
- usedvecs = irq_build_affinity_masks(affd, curvec, affvecs,
- node_to_cpumask, cpu_present_mask,
- nmsk, masks);
+ ret = __irq_build_affinity_masks(curvec, numvecs, firstvec,
+ node_to_cpumask, cpu_present_mask,
+ nmsk, masks);
+ if (ret < 0)
+ goto fail_build_affinity;
+ nr_present = ret;
/*
* Spread on non present CPUs starting from the next vector to be
@@ -220,15 +373,105 @@
* vector space, assign the non present CPUs to the already spread
* out vectors.
*/
- if (usedvecs >= affvecs)
- curvec = affd->pre_vectors;
+ if (nr_present >= numvecs)
+ curvec = firstvec;
else
- curvec = affd->pre_vectors + usedvecs;
+ curvec = firstvec + nr_present;
cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask);
- usedvecs += irq_build_affinity_masks(affd, curvec, affvecs,
- node_to_cpumask, npresmsk,
- nmsk, masks);
+ ret = __irq_build_affinity_masks(curvec, numvecs, firstvec,
+ node_to_cpumask, npresmsk, nmsk,
+ masks);
+ if (ret >= 0)
+ nr_others = ret;
+
+ fail_build_affinity:
put_online_cpus();
+
+ if (ret >= 0)
+ WARN_ON(nr_present + nr_others < numvecs);
+
+ free_node_to_cpumask(node_to_cpumask);
+
+ fail_npresmsk:
+ free_cpumask_var(npresmsk);
+
+ fail_nmsk:
+ free_cpumask_var(nmsk);
+ return ret < 0 ? ret : 0;
+}
+
+static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs)
+{
+ affd->nr_sets = 1;
+ affd->set_size[0] = affvecs;
+}
+
+/**
+ * irq_create_affinity_masks - Create affinity masks for multiqueue spreading
+ * @nvecs: The total number of vectors
+ * @affd: Description of the affinity requirements
+ *
+ * Returns the irq_affinity_desc pointer or NULL if allocation failed.
+ */
+struct irq_affinity_desc *
+irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
+{
+ unsigned int affvecs, curvec, usedvecs, i;
+ struct irq_affinity_desc *masks = NULL;
+
+ /*
+ * Determine the number of vectors which need interrupt affinities
+ * assigned. If the pre/post request exhausts the available vectors
+ * then nothing to do here except for invoking the calc_sets()
+ * callback so the device driver can adjust to the situation.
+ */
+ if (nvecs > affd->pre_vectors + affd->post_vectors)
+ affvecs = nvecs - affd->pre_vectors - affd->post_vectors;
+ else
+ affvecs = 0;
+
+ /*
+ * Simple invocations do not provide a calc_sets() callback. Install
+ * the generic one.
+ */
+ if (!affd->calc_sets)
+ affd->calc_sets = default_calc_sets;
+
+ /* Recalculate the sets */
+ affd->calc_sets(affd, affvecs);
+
+ if (WARN_ON_ONCE(affd->nr_sets > IRQ_AFFINITY_MAX_SETS))
+ return NULL;
+
+ /* Nothing to assign? */
+ if (!affvecs)
+ return NULL;
+
+ masks = kcalloc(nvecs, sizeof(*masks), GFP_KERNEL);
+ if (!masks)
+ return NULL;
+
+ /* Fill out vectors at the beginning that don't need affinity */
+ for (curvec = 0; curvec < affd->pre_vectors; curvec++)
+ cpumask_copy(&masks[curvec].mask, irq_default_affinity);
+
+ /*
+ * Spread on present CPUs starting from affd->pre_vectors. If we
+ * have multiple sets, build each sets affinity mask separately.
+ */
+ for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) {
+ unsigned int this_vecs = affd->set_size[i];
+ int ret;
+
+ ret = irq_build_affinity_masks(curvec, this_vecs,
+ curvec, masks);
+ if (ret) {
+ kfree(masks);
+ return NULL;
+ }
+ curvec += this_vecs;
+ usedvecs += this_vecs;
+ }
/* Fill out vectors at the end that don't need affinity */
if (usedvecs >= affvecs)
@@ -236,14 +479,12 @@
else
curvec = affd->pre_vectors + usedvecs;
for (; curvec < nvecs; curvec++)
- cpumask_copy(masks + curvec, irq_default_affinity);
+ cpumask_copy(&masks[curvec].mask, irq_default_affinity);
-outnodemsk:
- free_node_to_cpumask(node_to_cpumask);
-outnpresmsk:
- free_cpumask_var(npresmsk);
-outcpumsk:
- free_cpumask_var(nmsk);
+ /* Mark the managed interrupts */
+ for (i = affd->pre_vectors; i < nvecs - affd->post_vectors; i++)
+ masks[i].is_managed = 1;
+
return masks;
}
@@ -253,17 +494,22 @@
* @maxvec: The maximum number of vectors available
* @affd: Description of the affinity requirements
*/
-int irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity *affd)
+unsigned int irq_calc_affinity_vectors(unsigned int minvec, unsigned int maxvec,
+ const struct irq_affinity *affd)
{
- int resv = affd->pre_vectors + affd->post_vectors;
- int vecs = maxvec - resv;
- int ret;
+ unsigned int resv = affd->pre_vectors + affd->post_vectors;
+ unsigned int set_vecs;
if (resv > minvec)
return 0;
- get_online_cpus();
- ret = min_t(int, cpumask_weight(cpu_possible_mask), vecs) + resv;
- put_online_cpus();
- return ret;
+ if (affd->calc_sets) {
+ set_vecs = maxvec - resv;
+ } else {
+ get_online_cpus();
+ set_vecs = cpumask_weight(cpu_possible_mask);
+ put_online_cpus();
+ }
+
+ return resv + min(set_vecs, maxvec - resv);
}
--
Gitblit v1.6.2